Postdoctoral fellow in Computer Vision and Machine Learning Application deadline: August 18, 2025

Wasp Sweden; Göteborgs kommun; On-site; SEK 50,000 - 70,000; Full time

Job summary

A leading research organization in Gothenburg is offering a postdoctoral fellow position in Computer Vision and Machine Learning. The role involves conducting research on novel machine learning methods for scene interpretation and generative models, while collaborating with both academic and industrial partners. Candidates should have a relevant PhD and experience in machine learning, with responsibilities including supervising students and engaging in multidisciplinary research projects.

Qualifications

• PhD in a relevant field is required.
• Experience with generative models and machine learning.
• Strong research background in scene perception and image processing.

Responsibilities

• Conduct research on 3D scene perception and generative diffusion models.
• Supervise master's and PhD students as needed.
• Collaborate with researchers in a multidisciplinary environment.

Skills

Machine learning methodologies

Perceptual understanding

Generative models

Scene interpretation

Research collaboration

Education

PhD in Computer Vision, Machine Learning or related field

Tools

Neural networks

Programming in Python

Knowledge of 3D modeling tools

Job description

Postdoctoral fellow in Computer Vision and Machine Learning

August 18, 2025

Chalmers and the University of Gothenburg is currently offering a position as postdoctoral fellow in Computer Vision and Machine Learning. This multidisciplinary position is part of a WASP NEST (Novelty, Excellence, Synergy, Teams) project focused on advancing generative models and perceptual understanding in computer vision. The position is embedded in a vibrant research environment that includes several PhD students and postdoctoral researchers.

The project is a close collaboration between the Computer Vision Group at Chalmers, the Robotics, Perception and Learning Lab at KTH, and the Department of Mathematics at KTH. It also involves active engagement with industry partners, including H&M, Volvo Cars, Zenseact, and Embellence Group. The NEST initiative supports regular joint seminars, workshops, and research visits between participating institutions, fostering a dynamic and collaborative atmosphere.

In recent years, generative neural network models for creation of photo‑realistic images have become increasingly popular. Their training results in a low‑dimensional latent space representation of a distribution from which new examples can be drawn and images be generated. To be able to control and manipulate the images, one aims for a disentangled latent representation, so that different qualities of the resulting images are kept separate. For example, the shape of an object can be separated from its material properties, the viewing direction and the overall illumination. In this project, we will go one step further and develop disentangled latent representations, not just for individual objects, but for full three‑dimensional scenes with multiple objects that might change over time. The goal is to provide support for operations like adding, modifying and removing objects, changing scene conditions, modelling scene dynamics, as well as automatically completing missing parts of the 3D scene.

Main responsibilities

Your major responsibility as postdoc is to perform your own research in collaboration with other researchers within the NEST. The position also includes supervision of master’s and/or PhD students to a certain extent.

The successful candidate will contribute to the multidisciplinary project “3D Scene Perception, Embeddings and Neural Rendering”, led by Fredrik Kahl (Computer Vision, Chalmers), Kathlén Kohn (Algebraic Geometry, KTH), and Mårten Björkman (Robotics, Perception and Learning, KTH).

The research focuses on developing novel machine learning methods for scene interpretation and generative diffusion models. For more information, visit the project website: https://neural3d.github.io

The Computer Vision Group at the division of Signal processing and Biomedical Engineering develops intelligent systems for automatic image interpretation and perceptual scene understanding. Our research spans both foundational and applied topics in computer vision and machine learning, with particular strengths in inverse problems, generative models, and geometric deep learning.

We work across diverse application areas, from medical imaging—where we design advanced tools for diagnosis and decision support—to general vision tasks such as autonomous navigation, image‑based localization, 3D reconstruction, and object recognition. The group combines theoretical rigor with strong collaborative links to industry and academia, providing an intellectually stimulating environment for researchers interested in both deep technical challenges and real‑world impact.

The WASP newsletter gathers news, recent activities and upcoming events within the program.